search

hitachi-speech / EEND

End-to-End Neural Diarization
MIT License
377 stars 59 forks source link

PositionalEncoding does not used? #38

Closed kli017 closed 2 years ago

kli017 commented 2 years ago

Hello, in transformer.py I found that the pos_enc was initialized in the encoder but it was not used ind the forward?

DiLiangWU commented 2 years ago

They did not use positional encoding, as described in paper. [2] Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe, " End-to-End Neural Speaker Diarization with Self-attention," Proc. ASRU, pp. 296-303, 2019 image